Coding standards, frameworks, refactoring, and code review (18.4K skills)
Add review feedback directly to specific changed lines in a GitHub pull request. The skill explains how to post one comment or group several comments into a review, using an available inline-comment tool or GitHub CLI (`gh`).
Applies an incremental approach to coding, refactoring, system design, and workflow changes. It encourages error prevention through types and early validation, consistency with existing project patterns, and solutions sized to current needs instead of speculative complexity.
Review an open GitHub pull request and post concise, actionable comments directly on changed lines. The workflow checks eligibility, considers code quality and relevant risks, and filters findings by confidence and impact before commenting.
Create Claude slash commands through an interactive process. Clarify the command’s purpose, choose a category and project or user location, then draft its structure, supporting resources, and documentation using established patterns.
Build MCP servers that let LLMs work with external APIs and services. The guide covers workflow-focused tool design, implementation in Python with FastMCP or Node/TypeScript with the MCP SDK, error handling, review, and evaluations using realistic questions.
Breaks a task specification into implementation phases, delegates each step, and checks the completed work with an automated LLM review before moving on. It can also continue or refine work already in progress.
Delegate a task to an implementation agent, have a separate agent set tailored evaluation criteria and judge the result, then retry with specific feedback when needed. The process allows up to three retries before escalating unresolved issues.
Compare recent Git changes with the project’s FPF knowledge base to find context drift, evidence tied to changed files, and decisions that may need review. The skill reports findings and updates the baseline commit for the next audit.
Analyze a GitHub issue and the related project code, then create a structured technical specification covering the problem, proposed approach, implementation and test plans, affected files, and success criteria.
Create or update agent skills by testing how agents handle realistic scenarios before writing instructions. The guide adapts the RED-GREEN-REFACTOR cycle from test-driven development: observe failures, write targeted guidance, and test again to close gaps.
Structure an improvement effort as a measurable PDCA cycle: define the problem and a hypothesis, make a small change, compare results with a baseline, then standardize what worked or adjust the next experiment.
Review only unresolved pull request threads and check each comment against the current files, including uncommitted local changes. Resolve threads only when every requirement is met or the concern is obsolete, and report which threads remain open with reasons.
Use Git notes to attach review status, test results, audit details, or other metadata to commits without changing their hashes or rewriting history. This skill covers adding, viewing, organizing, sharing, merging, and preserving notes across rebases.
Load unresolved review threads from a GitHub pull request and turn them into focused Markdown task files under `.specs/comments/`. Group related feedback without duplicating work, preserve actionable suggestions, and leave GitHub comments and PRs unchanged.
Create and manage a linear chain of related branches and pull requests with gh-stack. Use it to split multi-part changes into reviewable layers, then inspect, update, sync, rebase, submit, or merge the stack.
Use these React and Next.js guidelines when building, reviewing, or refactoring application code. The rules cover data loading, bundle size, server and client performance, rendering, and re-renders, with examples of inefficient and improved patterns.
Review web interface code against the latest Web Interface Guidelines to identify issues in design, usability, and accessibility. Specify files or a file pattern, and receive concise findings with file names and line numbers.
Upgrade a project to the latest Next.js version by checking its current dependencies, following official migration guides, and applying codemods for code changes. The workflow also identifies manual updates and calls for build and development checks.
Apply practical Next.js guidance when writing or reviewing application code. It covers project files, Server and Client Component boundaries, data patterns, async APIs, routing, error handling, metadata, image and font optimization, and bundling.
Configure Next.js 16 Cache Components to combine prerendered, cached, and request-time content in one route. Set cache lifetimes and tags, invalidate data, and migrate older caching patterns while accounting for runtime and deployment limits.
Build and improve mobile apps with React Native and Expo using prioritized implementation rules. Covers faster lists, animations, images, navigation, state management, and native dependencies, with explanations and code examples for reviewing common implementation choices.
Refactor React components into reusable pieces with clearer interfaces. Provides patterns for replacing excessive boolean settings, sharing state through providers, and designing component libraries, with additional guidance for React 19 APIs.
Create, update, and review reusable instruction bundles for Unreal Engine agents. Get guidance on choosing a Python class or project asset, writing the description and instructions, registering the skill, and checking how it will appear to the agent.
Uses a live Unreal Editor connection through MCP to inspect and modify project state, such as actors, Blueprints, materials, and assets. It discovers the available tools before acting and checks results, making it suited to hands-on editor tasks rather than conceptual questions.